An image analysis method applicable to an electronic system is provided. The electronic system includes an image capture device. The image analysis method includes: obtaining a plurality of images captured by the image capture device; performing a motion detection on the plurality of images to determine whether the images include a motion; and determining whether a target enters the preset scenery or leaves the preset scenery in response to a determination that the plurality of images include the motion according to the motion detection.
Legal claims defining the scope of protection, as filed with the USPTO.
1. An image analysis method applicable to an electronic system comprising an image capture device, the image analysis method comprising: obtaining a plurality of images captured by the image capture device; performing a motion detection on the images to determine whether the images comprise a motion; and determining whether a target enters a preset scenery or leaves the preset scenery in response to the determination of the motion detected on the plurality of images by the motion detection, wherein the step of determining whether the target enters the preset scenery or leaves the preset scenery comprises: obtaining a follow-up image captured by the image capture device and performing an image analysis on the follow-up image to determine whether the target enters the preset scenery or leaves the preset scenery, wherein when the image analysis is performed on the follow-up image to determine whether the target enters the preset scenery or leaves the preset scenery, a capture time of the follow-up image is not earlier than a capture time of the images determined to comprise the motion.
2. The image analysis method of claim 1 , wherein the step of determining whether the target enters the preset scenery or leaves the preset scenery comprises: searching for the target in a scenery region of the follow-up image to determine whether the target enters the preset scenery according to whether the scenery region comprises the target, wherein the scenery region corresponds to the preset scenery.
3. The image analysis method of claim 1 , wherein after determining the images comprise the motion, the image analysis method further comprises: determining whether the motion enters the preset scenery.
4. The image analysis method of claim 1 , wherein after determining the images comprise the motion, the image analysis method further comprises: deciding a first region according to the motion; and defining a plurality of feature points in the first region.
5. The image analysis method of claim 4 , wherein the step of deciding the first region according to the motion comprises: obtaining a motion image of the images, wherein the motion image comprises a plurality of motion regions; filtering the motion regions according to an area of each motion region to keep at least one of the motion regions; and deciding the first region according to the at least one motion region kept.
6. The image analysis method of claim 5 , wherein the step of deciding the first region according to the at least one motion region kept comprises: selecting a target region from the at least one motion region according to the preset scenery; deciding the first region according to the target region, wherein a top edge of the first region is higher than a top edge of the target region.
7. The image analysis method of claim 4 , wherein the step of determining whether the target enters the preset scenery or leaves the preset scenery further comprises: obtaining optical flow information according to the feature points of the images; and deciding a motion direction according to the optical flow information.
8. The image analysis method of claim 7 , wherein the step of determining whether the target enters the preset scenery or leaves the preset scenery further comprises: determining whether the motion direction conforms to a preset entry direction; if the motion direction does not conform to the preset entry direction, determining the target does not enter the preset scenery; and if the motion direction conforms to the preset entry direction, obtaining a follow-up image captured by the image capture device and performing an image analysis on the follow-up image to determine whether the target enters the preset scenery.
9. The image analysis method of claim 7 , wherein the step of determining whether the target enters the preset scenery or leaves the preset scenery further comprises: determining whether the motion direction conforms to a preset exit direction; if the motion direction does not conform to the preset exit direction, determining the target does not leave the preset scenery; and if the motion direction conforms to the preset exit direction, obtaining a follow-up image captured by the image capture device and searching for the target in a scenery region of the follow-up image to determine whether the target leaves the preset scenery according to whether the scenery region comprises the target, wherein the scenery region corresponds to the preset scenery.
10. An electronic system, comprising: an image capture device; and a processor coupled to the image capture device and configured to: obtain a plurality of images captured by the image capture device; perform a motion detection on the images to determine whether the images comprise a motion; and determine whether a target enters a preset scenery or leaves the preset scenery in response to the determination of the motion detected on the plurality of images by the motion detection, wherein when determining whether the target enters the preset scenery or leaves the preset scenery, the processor is configured to: obtain a follow-up image captured by the image capture device and perform an image analysis on the follow-up image to determine whether the target enters the preset scenery or leaves the preset scenery, wherein when the processor performs the image analysis on the follow-up image to determine whether the target enters the preset scenery or leaves the preset scenery, a capture time of the follow-up image is not earlier than a capture time of the images determined to comprise the motion.
11. The electronic system of claim 10 , wherein when determining whether the target enters the preset scenery or leaves the preset scenery, the processor is configured to: search for the target in a scenery region of the follow-up image to determine whether the target enters the preset scenery according to whether the scenery region comprises the target, wherein the scenery region corresponds to the preset scenery.
12. The electronic system of claim 10 , wherein after determining the images comprise the motion, the processor is configured to: determine whether the motion enters the preset scenery.
13. The electronic system of claim 10 , wherein after determining the images comprise the motion, the processor is configured to: decide a first region according to the motion; and define a plurality of feature points in the first region.
14. The electronic system of claim 13 , wherein when deciding the first region according to the motion, the processor is configured to: obtain a motion image of the images, wherein the motion image comprises a plurality of motion regions; filter the motion regions according to an area of each motion region to keep at least one of the motion regions; and decide the first region according to the at least one motion region kept.
15. The electronic system of claim 14 , wherein when deciding the first region according to the at least one motion region kept, the processor is configured to: select a target region from the at least one motion region according to the preset scenery; decide the first region according to the target region, wherein a top edge of the first region is higher than a top edge of the target region.
16. The electronic system of claim 13 , wherein when determining whether the target enters the preset scenery or leaves the preset scenery, the processor is configured to: obtain optical flow information according to the feature points of the images; and decide a motion direction according to the optical flow information.
17. The electronic system of claim 16 , wherein when determining whether the target enters the preset scenery or leaves the preset scenery, the processor is configured to: determine whether the motion direction conforms to a preset entry direction; if the motion direction does not conform to the preset entry direction, determine the target does not enter the preset scenery; and if the motion direction conforms to the preset entry direction, obtain a follow-up image captured by the image capture device and perform an image analysis on the follow-up image to determine whether the target enters the preset scenery.
18. The electronic system of claim 16 , wherein when determining whether the target enters the preset scenery or leaves the preset scenery, the processor is configured to: determine whether the motion direction conforms to a preset exit direction; if the motion direction does not conform to the preset exit direction, determine the target does not leave the preset scenery; and if the motion direction conforms to the preset exit direction, obtain a follow-up image captured by the image capture device and search for the target in a scenery region of the follow-up image to determine whether the target leaves the preset scenery according to whether the scenery region comprises the target, wherein the scenery region corresponds to the preset scenery.
19. A non-transitory computer-readable recording medium storing a code, wherein an image analysis method can be completed when the code is loaded into a computer and executed, the image analysis method comprising: obtaining a plurality of images from an image capture device; performing a motion detection on the images to determine whether the images comprise a motion; and determining whether a target enters a preset scenery or leaves the preset scenery in response to the determination of the motion detected on the plurality of images by the motion detection, wherein the step of determining whether the target enters the preset scenery or leaves the preset scenery comprises: obtaining a follow-up image captured by the image capture device and performing an image analysis on the follow-up image to determine whether the target enters the preset scenery or leaves the preset scenery, wherein when the image analysis is performed on the follow-up image to determine whether the target enters the preset scenery or leaves the preset scenery, a capture time of the follow-up image is not earlier than a capture time of the images determined to comprise the motion.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 9, 2018
February 16, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.